Browse > Computer Vision > Zero-Shot Learning > Zero-Shot Action Recognition

Zero-Shot Action Recognition

118 papers with code ยท Computer Vision
Subtask of Zero-Shot Learning

The zero-shot action recognition aims to recognize unseen/novel action categories by exploiting semantics and seen/known actions

State-of-the-art leaderboards

Trend Dataset Best Method Paper title Paper Code Compare

Latest papers without code

Human Action Recognition with Multi-Laplacian Graph Convolutional Networks

15 Oct 2019

The main contribution of this method resides in a new design principle that learns graph-laplacians as convex combinations of other elementary laplacians each one dedicated to a particular topology of the input graphs.

ZERO-SHOT ACTION RECOGNITION

Generating Human Action Videos by Coupling 3D Game Engines and Probabilistic Graphical Models

12 Oct 2019

With this model we generate a diverse, realistic, and physically plausible dataset of human action videos, called PHAV for "Procedural Human Action Videos".

MOTION CAPTURE OPTICAL FLOW ESTIMATION REPRESENTATION LEARNING VIDEO GENERATION ZERO-SHOT ACTION RECOGNITION

Spatio-Temporal FAST 3D Convolutions for Human Action Recognition

30 Sep 2019

Motivated by the often distinctive temporal characteristics of actions in either horizontal or vertical direction, we introduce a novel convolution block for CNN architectures with video input.

ZERO-SHOT ACTION RECOGNITION

Learning deep representations for video-based intake gesture detection

24 Sep 2019

Automatic detection of individual intake gestures during eating occasions has the potential to improve dietary monitoring and support dietary recommendations.

ZERO-SHOT ACTION RECOGNITION

Global Temporal Representation based CNNs for Infrared Action Recognition

18 Sep 2019

Existing methods for infrared action recognition are either based on spatial or local temporal information, however, the global temporal information, which can better describe the movements of body parts across the whole video, is not considered.

OPTICAL FLOW ESTIMATION ZERO-SHOT ACTION RECOGNITION

Transferable Feature Representation for Visible-to-Infrared Cross-Dataset Human Action Recognition

18 Sep 2019

However, the infrared action data is limited until now, which degrades the performance of infrared action recognition.

DOMAIN ADAPTATION TRANSFER LEARNING ZERO-SHOT ACTION RECOGNITION

Adversarial Attack on Skeleton-based Human Action Recognition

14 Sep 2019

We also explore the possibility of semantically imperceptible localized attacks with CIASA, and succeed in fooling the state-of-the-art skeleton action recognition models with high confidence.

ADVERSARIAL ATTACK SKELETON BASED ACTION RECOGNITION

Metric-Based Few-Shot Learning for Video Action Recognition

14 Sep 2019

In this work, we address the task of few-shot video action recognition with a set of two-stream models.

FEW-SHOT LEARNING IMAGE CLASSIFICATION VIDEO CLASSIFICATION ZERO-SHOT ACTION RECOGNITION

Zero-Shot Action Recognition in Videos: A Survey

13 Sep 2019

Zero-Shot Action Recognition has attracted attention in the last years, and many approaches have been proposed for recognition of objects, events, and actions in images and videos.

ACTION RECOGNITION IN STILL IMAGES ACTION RECOGNITION IN VIDEOS VIDEO UNDERSTANDING

MLGCN: Multi-Laplacian Graph Convolutional Networks for Human Action Recognition

30th British Machine Vision Conference 2019

We also introduce a novel pooling operator, on graphs, that proceeds in two steps: context-dependent node expansion is achieved, followed by a global average pooling; the strength of this two-step process resides in its ability to preserve the discrimination power of nodes while achieving permutation invariance.

ACTION RECOGNITION IN VIDEOS SKELETON BASED ACTION RECOGNITION